Abstract
Accurate gender recognition from extreme long-range imagery remains a challenging problem due to limited spatial resolution, viewpoint variability, and loss of facial cues. For such purpose, we present a dual-path transformer framework that leverages CLIP to jointly model visual and attribute-driven cues for gender recognition at a distance. The framework integrates two complementary streams: (1) a direct visual path that refines a pre-trained CLIP image encoder through selective fine-tuning of its upper layers, and (2) an attribute-mediated path that infers gender from a set of soft-biometric prompts (e.g., hairstyle, clothing, accessories) aligned in the CLIP text-image space. Spatial channel attention modules further enhance discriminative localization under occlusion and low resolution. To support large-scale evaluation, we construct U-DetAGReID, a unified long-range gender dataset derived from DetReIDx and AG-ReID.v2, harmonized under a consistent ternary labeling scheme (Male, Female, Unknown). Extensive experiments suggest that the proposed solution surpasses state-of-the-art person-attribute and re-identification baselines across multiple metrics (macro-F1, accuracy, AUC), with consistent robustness to distance, angle, and height variations. Qualitative attention visualizations confirm interpretable attribute localization and responsible abstention behavior. Our results show that language-guided dual-path learning offers a principled, extensible foundation for responsible gender recognition in unconstrained long-range scenarios.
Abstract (translated)
从极端远距离图像中进行准确的性别识别仍然是一个挑战，原因在于空间分辨率有限、视角变化以及面部线索丢失。为此，我们提出了一种双路径Transformer框架，该框架利用CLIP（对比语言-图像预训练模型）来同时建模视觉和属性驱动的提示，以实现远程性别识别。此框架整合了两条互补的数据流：(1) 一条直接视觉路径，通过选择性微调其上层结构来优化预训练的CLIP图像编码器；(2) 一个由属性中介的路径，从一组软生物特征提示（如发型、服装和配饰）中推断性别，这些提示在CLIP文本-图像空间中进行了对齐。此外，空间通道注意模块进一步增强了遮挡和低分辨率条件下的区分性定位。 为了支持大规模评估，我们构建了U-DetAGReID数据集，该数据集是从DetReIDx和AG-ReID.v2派生而来的统一远距离性别识别数据集，并在一致的三元标签体系（男性、女性、未知）下进行了调和。广泛的实验表明，所提出的解决方案在多种度量标准（宏F1分数、准确率、AUC）上超越了现有的人员属性和重识别基准方法，在不同距离、角度和高度变化的情况下均表现出稳健性。定性的注意可视化确认了可解释的属性定位及合理的放弃行为。 我们的研究结果表明，语言引导的双路径学习为在无约束远距离场景中进行负责任的性别识别提供了一个合理且可扩展的基础。
URL
https://arxiv.org/abs/2512.06426
